X

Xora Innovation

Funding AI and deep tech ventures

Senior / Principal Computational Materials Scientist

Applied Machine LearningConfirmed live in the last 24 hours
Full-timeSan Diego, CA, USANo salary listed

About the Job

Requirements

  • A PhD in chemistry, physics, materials science, chemical engineering, or a closely related field is required.
  • At least 5 years of post-PhD industry experience at a semiconductor integrated device manufacturer, foundry, equipment original equipment manufacturer, materials or precursor supplier, or electronic design automation or molecular-modeling software company is required.
  • Demonstrated production use of density functional theory, such as VASP, Quantum ESPRESSO, CP2K, QuantumATK, Gaussian, ORCA, or equivalent, on semiconductor-relevant chemistry including deposition, etch, doping, interfaces, or defects is required.
  • Hands-on molecular dynamics experience, including force-field or machine-learned interatomic potential selection, validation, and interpretation, is required.
  • Working familiarity with process simulation or technology computer-aided design, such as Sentaurus or Victory, and understanding how atomistic results translate to process outcomes is required.
  • Strong Python skills and comfort building and automating workflows with tools such as ASE, pymatgen, AiiDA, FireWorks, or similar are required.
  • A track record of predictions that changed an experimental or engineering decision is required.

Responsibilities

  • Model precursor chemistry, surface reactions, and thin-film growth and etch mechanisms using periodic and molecular density functional theory, ranking pathways for atomic layer deposition, atomic layer etching, chemical vapor deposition, and epitaxy processes.
  • Build, train, and fine-tune machine-learned interatomic potentials on density functional theory data and deploy them in large-scale molecular dynamics and kinetic simulations.
  • Run classical and reactive molecular dynamics using LAMMPS and ReaxFF for film nucleation, defect evolution, interface formation, and plasma–surface interaction.
  • Bridge atomistic results into continuum and process-level models, such as Sentaurus Process, Victory Process, and custom kinetic Monte Carlo, to predict conformality, selectivity, throughput, and device-relevant film properties.
  • Design simulation campaigns that feed active-learning and generative models, defining what is computed, at what fidelity, and why.
  • Work directly with customer process engineers at integrated device manufacturers, foundries, original equipment manufacturers, and materials suppliers to validate predictions against experimental and fab data.
  • Establish reproducible, automated simulation infrastructure, including workflow managers, high-performance-computing or cloud orchestration, and data provenance.

Desired Qualifications

  • Experience training or fine-tuning machine-learned interatomic potentials or universal potentials, and understanding when they fail.
  • Kinetic Monte Carlo or microkinetic modeling of surface processes.
  • Exposure to plasma chemistry modeling for etch or plasma-enhanced atomic layer deposition.
  • Publications or patents in atomic layer deposition or atomic layer etching mechanisms, precursor design, or process modeling.
  • Prior work with customer-facing technical validation in a fab or supplier setting.
  • Detailed knowledge of semiconductor manufacturing processes and materials.

About the Company

Xora Innovation

Funding AI and deep tech ventures

placeholder

Company size
11-50
Company stage
Not listed
Total funding
$1.8B
Headquarters
Singapore, Singapore
Founded
2019

Recently Posted Jobs

Explore more opportunities at Xora Innovation

See more jobs